yerevann commited on
Commit
f7644f4
1 Parent(s): fad79b7

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +91 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +790 -0
special_tokens_map.json ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "[SYNONYM]",
4
+ "[RELATED]",
5
+ "[SIMILAR]",
6
+ "[PROPERTY]",
7
+ "[SAS]",
8
+ "[WEIGHT]",
9
+ "[TPSA]",
10
+ "[CLOGP]",
11
+ "[QED]",
12
+ "[NUMHDONORS]",
13
+ "[NUMHACCEPTORS]",
14
+ "[NUMHETEROATOMS]",
15
+ "[NUMROTATABLEBONDS]",
16
+ "[NOCOUNT]",
17
+ "[NHOHCOUNT]",
18
+ "[RINGCOUNT]",
19
+ "[HEAVYATOMCOUNT]",
20
+ "[FRACTIONCSP3]",
21
+ "[NUMAROMATICRINGS]",
22
+ "[NUMSATURATEDRINGS]",
23
+ "[NUMAROMATICHETEROCYCLES]",
24
+ "[NUMAROMATICCARBOCYCLES]",
25
+ "[NUMSATURATEDHETEROCYCLES]",
26
+ "[NUMSATURATEDCARBOCYCLES]",
27
+ "[NUMALIPHATICRINGS]",
28
+ "[NUMALIPHATICHETEROCYCLES]",
29
+ "[NUMALIPHATICCARBOCYCLES]",
30
+ "[IUPAC]",
31
+ "[VAR_NAME]",
32
+ "[VAR_DESC]",
33
+ "[VAR_VAL]",
34
+ "[ASSAY_NAME]",
35
+ "[ASSAY_DESC]",
36
+ "[/SYNONYM]",
37
+ "[/RELATED]",
38
+ "[/SIMILAR]",
39
+ "[/PROPERTY]",
40
+ "[/SAS]",
41
+ "[/WEIGHT]",
42
+ "[/TPSA]",
43
+ "[/CLOGP]",
44
+ "[/QED]",
45
+ "[/NUMHDONORS]",
46
+ "[/NUMHACCEPTORS]",
47
+ "[/NUMHETEROATOMS]",
48
+ "[/NUMROTATABLEBONDS]",
49
+ "[/NOCOUNT]",
50
+ "[/NHOHCOUNT]",
51
+ "[/RINGCOUNT]",
52
+ "[/HEAVYATOMCOUNT]",
53
+ "[/FRACTIONCSP3]",
54
+ "[/NUMAROMATICRINGS]",
55
+ "[/NUMSATURATEDRINGS]",
56
+ "[/NUMAROMATICHETEROCYCLES]",
57
+ "[/NUMAROMATICCARBOCYCLES]",
58
+ "[/NUMSATURATEDHETEROCYCLES]",
59
+ "[/NUMSATURATEDCARBOCYCLES]",
60
+ "[/NUMALIPHATICRINGS]",
61
+ "[/NUMALIPHATICHETEROCYCLES]",
62
+ "[/NUMALIPHATICCARBOCYCLES]",
63
+ "[/IUPAC]",
64
+ "[/VAR_NAME]",
65
+ "[/VAR_DESC]",
66
+ "[/VAR_VAL]",
67
+ "[/ASSAY_NAME]",
68
+ "[/ASSAY_DESC]"
69
+ ],
70
+ "bos_token": {
71
+ "content": "<s>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false
76
+ },
77
+ "eos_token": {
78
+ "content": "</s>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false
83
+ },
84
+ "pad_token": {
85
+ "content": "<pad>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false
90
+ }
91
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,790 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[START_REF]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "[END_REF]",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "[IMAGE]",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "7": {
60
+ "content": "<fragments>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "8": {
68
+ "content": "</fragments>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "9": {
76
+ "content": "<work>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "10": {
84
+ "content": "</work>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "11": {
92
+ "content": "[START_SUP]",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "12": {
100
+ "content": "[END_SUP]",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "13": {
108
+ "content": "[START_SUB]",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "14": {
116
+ "content": "[END_SUB]",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "15": {
124
+ "content": "[START_DNA]",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "16": {
132
+ "content": "[END_DNA]",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "17": {
140
+ "content": "[START_AMINO]",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "18": {
148
+ "content": "[END_AMINO]",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "19": {
156
+ "content": "[START_SMILES]",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "20": {
164
+ "content": "[END_SMILES]",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "21": {
172
+ "content": "[START_I_SMILES]",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "22": {
180
+ "content": "[END_I_SMILES]",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "50000": {
188
+ "content": "[SYNONYM]",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "50001": {
196
+ "content": "[RELATED]",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "50002": {
204
+ "content": "[SIMILAR]",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "50003": {
212
+ "content": "[PROPERTY]",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "50004": {
220
+ "content": "[SAS]",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "50005": {
228
+ "content": "[WEIGHT]",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "50006": {
236
+ "content": "[TPSA]",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "50007": {
244
+ "content": "[CLOGP]",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "50008": {
252
+ "content": "[QED]",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "50009": {
260
+ "content": "[NUMHDONORS]",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "50010": {
268
+ "content": "[NUMHACCEPTORS]",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "50011": {
276
+ "content": "[NUMHETEROATOMS]",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "50012": {
284
+ "content": "[NUMROTATABLEBONDS]",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "50013": {
292
+ "content": "[NOCOUNT]",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "50014": {
300
+ "content": "[NHOHCOUNT]",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "50015": {
308
+ "content": "[RINGCOUNT]",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "50016": {
316
+ "content": "[HEAVYATOMCOUNT]",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "50017": {
324
+ "content": "[FRACTIONCSP3]",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "50018": {
332
+ "content": "[NUMAROMATICRINGS]",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "50019": {
340
+ "content": "[NUMSATURATEDRINGS]",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "50020": {
348
+ "content": "[NUMAROMATICHETEROCYCLES]",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "50021": {
356
+ "content": "[NUMAROMATICCARBOCYCLES]",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "50022": {
364
+ "content": "[NUMSATURATEDHETEROCYCLES]",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "50023": {
372
+ "content": "[NUMSATURATEDCARBOCYCLES]",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "50024": {
380
+ "content": "[NUMALIPHATICRINGS]",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "50025": {
388
+ "content": "[NUMALIPHATICHETEROCYCLES]",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "50026": {
396
+ "content": "[NUMALIPHATICCARBOCYCLES]",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "50027": {
404
+ "content": "[IUPAC]",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "50028": {
412
+ "content": "[VAR_NAME]",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "50029": {
420
+ "content": "[VAR_DESC]",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "50030": {
428
+ "content": "[VAR_VAL]",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "50031": {
436
+ "content": "[ASSAY_NAME]",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "50032": {
444
+ "content": "[ASSAY_DESC]",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "50033": {
452
+ "content": "[/SYNONYM]",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "50034": {
460
+ "content": "[/RELATED]",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "50035": {
468
+ "content": "[/SIMILAR]",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "50036": {
476
+ "content": "[/PROPERTY]",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "50037": {
484
+ "content": "[/SAS]",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "50038": {
492
+ "content": "[/WEIGHT]",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "50039": {
500
+ "content": "[/TPSA]",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "50040": {
508
+ "content": "[/CLOGP]",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "50041": {
516
+ "content": "[/QED]",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "50042": {
524
+ "content": "[/NUMHDONORS]",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "50043": {
532
+ "content": "[/NUMHACCEPTORS]",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "50044": {
540
+ "content": "[/NUMHETEROATOMS]",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "50045": {
548
+ "content": "[/NUMROTATABLEBONDS]",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "50046": {
556
+ "content": "[/NOCOUNT]",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "50047": {
564
+ "content": "[/NHOHCOUNT]",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "50048": {
572
+ "content": "[/RINGCOUNT]",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "50049": {
580
+ "content": "[/HEAVYATOMCOUNT]",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "50050": {
588
+ "content": "[/FRACTIONCSP3]",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "50051": {
596
+ "content": "[/NUMAROMATICRINGS]",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "50052": {
604
+ "content": "[/NUMSATURATEDRINGS]",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "50053": {
612
+ "content": "[/NUMAROMATICHETEROCYCLES]",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "50054": {
620
+ "content": "[/NUMAROMATICCARBOCYCLES]",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "50055": {
628
+ "content": "[/NUMSATURATEDHETEROCYCLES]",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "50056": {
636
+ "content": "[/NUMSATURATEDCARBOCYCLES]",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "50057": {
644
+ "content": "[/NUMALIPHATICRINGS]",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "50058": {
652
+ "content": "[/NUMALIPHATICHETEROCYCLES]",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "50059": {
660
+ "content": "[/NUMALIPHATICCARBOCYCLES]",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "50060": {
668
+ "content": "[/IUPAC]",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "50061": {
676
+ "content": "[/VAR_NAME]",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "50062": {
684
+ "content": "[/VAR_DESC]",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "50063": {
692
+ "content": "[/VAR_VAL]",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "50064": {
700
+ "content": "[/ASSAY_NAME]",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "50065": {
708
+ "content": "[/ASSAY_DESC]",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ }
715
+ },
716
+ "additional_special_tokens": [
717
+ "[SYNONYM]",
718
+ "[RELATED]",
719
+ "[SIMILAR]",
720
+ "[PROPERTY]",
721
+ "[SAS]",
722
+ "[WEIGHT]",
723
+ "[TPSA]",
724
+ "[CLOGP]",
725
+ "[QED]",
726
+ "[NUMHDONORS]",
727
+ "[NUMHACCEPTORS]",
728
+ "[NUMHETEROATOMS]",
729
+ "[NUMROTATABLEBONDS]",
730
+ "[NOCOUNT]",
731
+ "[NHOHCOUNT]",
732
+ "[RINGCOUNT]",
733
+ "[HEAVYATOMCOUNT]",
734
+ "[FRACTIONCSP3]",
735
+ "[NUMAROMATICRINGS]",
736
+ "[NUMSATURATEDRINGS]",
737
+ "[NUMAROMATICHETEROCYCLES]",
738
+ "[NUMAROMATICCARBOCYCLES]",
739
+ "[NUMSATURATEDHETEROCYCLES]",
740
+ "[NUMSATURATEDCARBOCYCLES]",
741
+ "[NUMALIPHATICRINGS]",
742
+ "[NUMALIPHATICHETEROCYCLES]",
743
+ "[NUMALIPHATICCARBOCYCLES]",
744
+ "[IUPAC]",
745
+ "[VAR_NAME]",
746
+ "[VAR_DESC]",
747
+ "[VAR_VAL]",
748
+ "[ASSAY_NAME]",
749
+ "[ASSAY_DESC]",
750
+ "[/SYNONYM]",
751
+ "[/RELATED]",
752
+ "[/SIMILAR]",
753
+ "[/PROPERTY]",
754
+ "[/SAS]",
755
+ "[/WEIGHT]",
756
+ "[/TPSA]",
757
+ "[/CLOGP]",
758
+ "[/QED]",
759
+ "[/NUMHDONORS]",
760
+ "[/NUMHACCEPTORS]",
761
+ "[/NUMHETEROATOMS]",
762
+ "[/NUMROTATABLEBONDS]",
763
+ "[/NOCOUNT]",
764
+ "[/NHOHCOUNT]",
765
+ "[/RINGCOUNT]",
766
+ "[/HEAVYATOMCOUNT]",
767
+ "[/FRACTIONCSP3]",
768
+ "[/NUMAROMATICRINGS]",
769
+ "[/NUMSATURATEDRINGS]",
770
+ "[/NUMAROMATICHETEROCYCLES]",
771
+ "[/NUMAROMATICCARBOCYCLES]",
772
+ "[/NUMSATURATEDHETEROCYCLES]",
773
+ "[/NUMSATURATEDCARBOCYCLES]",
774
+ "[/NUMALIPHATICRINGS]",
775
+ "[/NUMALIPHATICHETEROCYCLES]",
776
+ "[/NUMALIPHATICCARBOCYCLES]",
777
+ "[/IUPAC]",
778
+ "[/VAR_NAME]",
779
+ "[/VAR_DESC]",
780
+ "[/VAR_VAL]",
781
+ "[/ASSAY_NAME]",
782
+ "[/ASSAY_DESC]"
783
+ ],
784
+ "bos_token": "<s>",
785
+ "clean_up_tokenization_spaces": true,
786
+ "eos_token": "</s>",
787
+ "model_max_length": 1000000000000000019884624838656,
788
+ "pad_token": "<pad>",
789
+ "tokenizer_class": "PreTrainedTokenizerFast"
790
+ }